MIMO Speech Compression and Enhancement Based on Convolutional Denoising Autoencoder

2020-05-24 · You-Jin Li, Syu-Siang Wang, Yu Tsao, Borching Su

For speech-related applications in IoT environments, identifying effective methods to handle interference noises and compress the amount of data in transmissions is essential to achieve high-quality services. In this study, we propose a novel multi-input multi-output speech compression and enhancement (MIMO-SCE) system based on a convolutional denoising autoencoder (CDAE) model to simultaneously improve speech quality and reduce the dimensions of transmission data. Compared with conventional single-channel and multi-input single-output systems, MIMO systems can be employed in applications that handle multiple acoustic signals need to be handled. We investigated two CDAE models, a fully convolutional network (FCN) and a Sinc FCN, as the core models in MIMO systems. The experimental results confirm that the proposed MIMO-SCE framework effectively improves speech quality and intelligibility while reducing the amount of recording data by a factor of 7 for transmission.

📄 PDF Abstract BibTeX arXiv:2005.11704

Code (0)

등록된 구현이 없습니다.

Tasks

Denoising

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…

FCN Fully Convolutional Networks, or FCNs, are an architecture used mainly for semantic segmentation. They employ solely locally connected layers, such as…

The PCG-AIID System for L3DAS22 Challenge: MIMO and MISO convolutional recurrent Network for Multi Channel Speech Enhancement and Speech Recognition

2022-02-21 · Jingdong Li, Yuanyuan Zhu, Dawei Luo, Yun Liu 외

This paper described the PCG-AIID system for L3DAS22 challenge in Task 1: 3D speech enhancement in office reverberant environment. We proposed a two-stage framework to address multi-channel speech denoising and dereverbe…

Denoising Speech Denoising Speech Enhancement speech-recognition+1

Test-Time Adaptation Toward Personalized Speech Enhancement: Zero-Shot Learning with Knowledge Distillation

2021-05-08 · Sunwoo Kim, Minje Kim

In realistic speech enhancement settings for end-user devices, we often encounter only a few speakers and noise types that tend to reoccur in the specific acoustic environment. We propose a novel personalized speech enha…

Denoising Knowledge Distillation Model Compression Specificity+3

Lite Audio-Visual Speech Enhancement

2020-05-24 · Shang-Yi Chuang, Yu Tsao, Chen-Chou Lo, Hsin-Min Wang

Previous studies have confirmed the effectiveness of incorporating visual information into speech enhancement (SE) systems. Despite improved denoising performance, two problems may be encountered when implementing an aud…

Data Compression Denoising Speech Enhancement

Raw Waveform-based Speech Enhancement by Fully Convolutional Networks

2017-03-07 · Szu-Wei Fu, Yu Tsao, Xugang Lu, Hisashi Kawai

This study proposes a fully convolutional network (FCN) model for raw waveform-based speech enhancement. The proposed system performs speech enhancement in an end-to-end (i.e., waveform-in and waveform-out) manner, which…

Denoising Speech Enhancement

spatial-dccrn: dccrn equipped with frame-level angle feature and hybrid filtering for multi-channel speech enhancement

2022-10-17 · Shubo Lv, Yihui Fu, Yukai Jv, Lei Xie 외

Recently, multi-channel speech enhancement has drawn much interest due to the use of spatial information to distinguish target speech from interfering signal. To make full use of spatial information and neural network ba…